Browsing by Author "Anderson, Connor"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Mapping Invasive Phragmites australis Using Unmanned Aircraft System Imagery, Canopy Height Models, and Synthetic Aperture Radar
    (2020-11) Anderson, Connor
    Invasive plant species are an increasing worldwide threat both financially and ecologically. Knowing the location of these invasive plant infestations is the first step in their control. Surveying for Phragmites australis is particularly challenging due to limited accessibility in wetland environments. Unmanned aircraft systems (UASs) are a popular choice for invasive species management due to their ability to survey challenging environments and their high spatial and temporal resolution. This study tested the utility of three-band (i.e., red, green, and blue; RGB) UAS imagery for mapping Phragmites in the St. Louis River Estuary in Minnesota, U.S.A. and Saginaw Bay in Michigan, U.S.A. Iterative object-based image analysis techniques were used to identify two classes, Phragmites and Not Phragmites. Additionally, the effectiveness of canopy height models (CHMs) created from two data types, UAS imagery and commercial satellite stereo retrievals, and the RADARSAT-2 horizontal-horizontal (HH) polarization were tested for Phragmites identification. The highest overall classification accuracy of 90.2% was achieved when pairing the UAS imagery with a UAS-derived CHM. Producer’s accuracy for the Phragmites class ranged from 2.7 to 75.6%, and the user’s accuracies were above 90%. The Not Phragmites class had user’s and producer’s accuracies above 88%. Inclusion of the RADARSAT-2 HH polarization caused a slight reduction in classification accuracy. Commercial satellite stereo retrievals increased commission errors due to decreased spatial resolution and vertical accuracy. The lowest overall classification accuracy was seen when using only the RGB UAS imagery. UASs are promising for Phragmites identification, but the imagery should be used in conjunction with a CHM.
  • Thumbnail Image
    Item
    Mississippi River Corridor Restoration Site Analysis
    (Resilient Communities Project (RCP), University of Minnesota, 2014) Barnhart, Caitlin; Ellingson, Emily; Ogdahl, Eric; Ponath, Nicole; Anderson, Connor; Barnes, Michael; Shaughnessy, Aidan; Madaus, Cody; Butler, Megan; Singh, Niluja; Unzeitig, Matthew M
    This project was completed as part of a year-long partnership between the City of Rosemount and the University of Minnesota’s Resilient Communities Project (http://www.rcp.umn.edu). The City of Rosemount includes a stretch of land along the Mississippi River—the site of a planned regional bike trail. The area around the proposed bike trail is in a somewhat degraded state today after years of animal grazing and human use, with many nonnative species in need of control. Several different entities, including Flint Hills Resources, CF Industries, and Dakota County, currently own portions of the riverfront property. The goal of this project was to convene relevant stakeholders and land owners, evaluate existing restoration activities in the Mississippi River Critical Area Corridor, and recommend an overall restoration strategy or plan that builds on these efforts and incorporates additional public access opportunities. In collaboration with city project lead Eric Zweber, a planner for the City of Rosemount, four teams of students in HORT 5071: Ecological Restoration assessed the condition of the land and ecosystems and designed a master plan for restoration of approximately 70 acres of the riverfront after the planned bike trail is in place. A group presentation from the project is available highlighting overall restoration goals and an overview of recommendations, in addition to reports for each of the four restoration areas.
  • Thumbnail Image
    Item
    Semi-Automated Detection of Invasive Phragmites australis Using Uncrewed Aircraft Systems
    (2023-06) Anderson, Connor
    Surveying methods for invasive plant species need modernization. Cataloging the exact location of invasive plant populations has traditionally focused on in situ monitoring. Such methods are often hindered by resource limitations, access to private property, and physical inaccessibility of remote locations. Surveying for invasive Phragmites australis is particularly difficult due to the limited accessibility in the wetland environments it invades. Remotely sensed data offers the ability to detect invasive Phragmites australis without the need for extensive physical mapping. Uncrewed aircraft systems (UAS) are a popular tool when surveilling for invasive plant species due to their ability to image challenging environments and their high spatial and temporal resolution. Additionally, UAS are unique in that the imagery can be used to create 3D models of the Earth’s surface.This dissertation demonstrates the efficacy of UAS for the identification of invasive Phragmites australis in multiple Minnesota and Michigan wetlands. The primary goal is to provide resource specialists managing for invasive Phragmites australis the information needed to implement UAS for Phragmites australis detection. Three major components are included within this dissertation. First, an object-based image analysis workflow was developed to classify Phragmites australis within Minnesota and Michigan wetlands from three-band (i.e., red, green, blue; RGB) UAS imagery. Second, a study investigating the ability of different machine learning algorithms to identify Phragmites australis within Minnesota wetlands is presented. Methods for improving machine learning classifications with object-based techniques are also described. The final study investigated the ability of five-band (i.e., red, green, blue, red edge, and near-infrared) multispectral UAS imagery to identify Phragmites australis. Voting-based ensemble classifiers were employed to classify Phragmites australis within five Minnesota wetlands. Classifications using the multispectral UAS imagery were compared to classifications using RGB UAS imagery. This research provides critically needed information on the data and methodology required to accurately identify Phragmites australis using UAS.